class ChunkSentenceSplitter extends AnnotatorModel[ChunkSentenceSplitter] with HasSimpleAnnotate[ChunkSentenceSplitter] with CheckLicense

An annotator that splits a document into sentences based on provided chunks. The first piece of the document is treated as a header, and subsequent chunks are labeled with their associated entities.

This annotator is particularly useful when identifying titles and subtitles using Named Entity Recognition (NER), followed by a paragraph-level split.

Example

// Create a DataFrame with a "text" column
val data = Seq(text, text).toDS.toDF("text")

// Set up the NLP pipeline with DocumentAssembler, RegexMatcher, and ChunkSentenceSplitter
val documentAssembler = new DocumentAssembler().setInputCol("text").setOutputCol("doc")
val regexMatcher = new RegexMatcher().setInputCols("doc").setOutputCol("chunks")
                  .setExternalRules("src/test/resources/chunker/title_regex.txt", ",")
val chunkSentenceSplitter = new ChunkSentenceSplitter().setInputCols("chunks", "doc").setOutputCol("paragraphs")
val pipeline = new Pipeline().setStages(Array(documentAssembler, regexMatcher, chunkSentenceSplitter))

// Fit the pipeline to the data and transform it
val result = pipeline.fit(data).transform(data).select("paragraphs")
result.show(truncate = false)
Linear Supertypes
CheckLicense, HasSimpleAnnotate[ChunkSentenceSplitter], AnnotatorModel[ChunkSentenceSplitter], CanBeLazy, RawAnnotator[ChunkSentenceSplitter], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[ChunkSentenceSplitter], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. ChunkSentenceSplitter
  2. CheckLicense
  3. HasSimpleAnnotate
  4. AnnotatorModel
  5. CanBeLazy
  6. RawAnnotator
  7. HasOutputAnnotationCol
  8. HasInputAnnotationCols
  9. HasOutputAnnotatorType
  10. ParamsAndFeaturesWritable
  11. HasFeatures
  12. DefaultParamsWritable
  13. MLWritable
  14. Model
  15. Transformer
  16. PipelineStage
  17. Logging
  18. Params
  19. Serializable
  20. Serializable
  21. Identifiable
  22. AnyRef
  23. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ChunkSentenceSplitter()
  2. new ChunkSentenceSplitter(uid: String)

    uid

    a unique identifier for the instantiated AnnotatorModel

Type Members

  1. type AnnotationContent = Seq[Row]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]

    annotations

    a Sequence of chunks to transform

    returns

    a Sequence of Merged CHUNK Annotations

    Definition Classes
    ChunkSentenceSplitter → HasSimpleAnnotate
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String], metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  16. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  17. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  18. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  19. final def clear(param: Param[_]): ChunkSentenceSplitter.this.type
    Definition Classes
    Params
  20. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  21. def copy(extra: ParamMap): ChunkSentenceSplitter
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  22. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  24. val defaultEntity: Param[String]

    String parameter representing the default name for the entity assigned to content between the start of the document and the first labeled chunk.

    String parameter representing the default name for the entity assigned to content between the start of the document and the first labeled chunk.

    Note

    Default: introduction

  25. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  26. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  27. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  28. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  29. def explainParams(): String
    Definition Classes
    Params
  30. final val extraInputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  31. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  32. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  33. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  34. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  35. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  36. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  37. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  40. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  41. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  42. def getChunksEntitiesBySentence(annotations: Seq[Annotation]): Seq[Seq[Annotation]]
  43. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  44. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  45. def getDefaultEntity(): String
  46. def getGroupBySentences(): Boolean
  47. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  48. def getInsertChunk(): Boolean
  49. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  50. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  51. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  52. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  53. val groupBySentences: BooleanParam

    This parameter determines whether to split a document into paragraphs by grouping chunks by sentences.

    This parameter determines whether to split a document into paragraphs by grouping chunks by sentences. If set to false, it assumes a single document annotation for all chunks. Set to true if you want to group chunks by sentences, and the input column of your chunk annotator is generated by a sentence detector.

    Note

    Default: true

  54. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  55. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  56. def hasParent: Boolean
    Definition Classes
    Model
  57. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  58. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  59. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  60. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator types: DOCUMENT,CHUNK

    Input annotator types: DOCUMENT,CHUNK

    Definition Classes
    ChunkSentenceSplitter → HasInputAnnotationCols
  61. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  62. val insertChunk: BooleanParam

    Boolean parameter that determines whether to include the chunk in the resulting sentences or not.

    Boolean parameter that determines whether to include the chunk in the resulting sentences or not.

    When insertChunk is set to true, the chunk will be added to the generated sentences. If set to false, the chunk will be omitted from the sentences.

    Note

    Default: true

  63. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  64. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  65. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  66. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  67. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  68. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  69. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  76. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  81. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  82. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  83. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  84. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  85. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  86. val outputAnnotatorType: AnnotatorType

    Output annotator types: CHUNK

    Output annotator types: CHUNK

    Definition Classes
    ChunkSentenceSplitter → HasOutputAnnotatorType
  87. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  88. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  89. var parent: Estimator[ChunkSentenceSplitter]
    Definition Classes
    Model
  90. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  91. def set[T](feature: StructFeature[T], value: T): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  92. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def set[T](feature: SetFeature[T], value: Set[T]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. def set[T](feature: ArrayFeature[T], value: Array[T]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  95. final def set(paramPair: ParamPair[_]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    Params
  96. final def set(param: String, value: Any): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    Params
  97. final def set[T](param: Param[T], value: T): ChunkSentenceSplitter.this.type
    Definition Classes
    Params
  98. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  99. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  100. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. final def setDefault(paramPairs: ParamPair[_]*): ChunkSentenceSplitter.this.type
    Attributes
    protected
    Definition Classes
    Params
  103. final def setDefault[T](param: Param[T], value: T): ChunkSentenceSplitter.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  104. def setDefaultEntity(value: String): ChunkSentenceSplitter.this.type

    Sets defaultEntity, defining the default name for the entity that represents content between the beginning of the document and the first chunk.

    Sets defaultEntity, defining the default name for the entity that represents content between the beginning of the document and the first chunk.

    returns

    This instance with the updated initEntityName property.

    Note

    Default: introduction

  105. def setExtraInputCols(value: Array[String]): ChunkSentenceSplitter.this.type
    Definition Classes
    HasInputAnnotationCols
  106. def setGroupBySentences(value: Boolean): ChunkSentenceSplitter.this.type

    Sets groupBySentences, which determines whether to split a document into paragraphs by grouping chunks by sentences.

    Sets groupBySentences, which determines whether to split a document into paragraphs by grouping chunks by sentences. If set to false, it assumes a single document annotation for all chunks. Set to true if you want to group chunks by sentences, and the input column of your chunk annotator is generated by a sentence detector.

    returns

    This instance with the updated groupBySentences property.

    Note

    Default: true

  107. final def setInputCols(value: String*): ChunkSentenceSplitter.this.type
    Definition Classes
    HasInputAnnotationCols
  108. def setInputCols(value: Array[String]): ChunkSentenceSplitter.this.type
    Definition Classes
    HasInputAnnotationCols
  109. def setInsertChunk(value: Boolean): ChunkSentenceSplitter.this.type

    Sets the value for the insertChunk parameter, determining whether to include the chunk in the resulting sentences or not.

    Sets the value for the insertChunk parameter, determining whether to include the chunk in the resulting sentences or not.

    When insertChunk is set to true, the chunk will be added to the generated sentences. If set to false, the chunk will be omitted from the sentences.

    returns

    This instance with the updated insertChunk property.

    Note

    Default: true

  110. def setLazyAnnotator(value: Boolean): ChunkSentenceSplitter.this.type
    Definition Classes
    CanBeLazy
  111. final def setOutputCol(value: String): ChunkSentenceSplitter.this.type
    Definition Classes
    HasOutputAnnotationCol
  112. def setParent(parent: Estimator[ChunkSentenceSplitter]): ChunkSentenceSplitter
    Definition Classes
    Model
  113. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  114. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  115. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  116. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  117. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  118. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  119. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  120. val uid: String
    Definition Classes
    ChunkSentenceSplitter → Identifiable
  121. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  122. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  123. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  124. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  125. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  126. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from CheckLicense

Inherited from HasSimpleAnnotate[ChunkSentenceSplitter]

Inherited from AnnotatorModel[ChunkSentenceSplitter]

Inherited from CanBeLazy

Inherited from RawAnnotator[ChunkSentenceSplitter]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[ChunkSentenceSplitter]

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

Annotator types

Required input and expected output annotator types

Members

Parameter setters